RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...)

kaijieshi7 / Dynamic-convolution-Pytorch

Pytorch!!!Pytorch!!!Pytorch!!! Dynamic Convolution: Attention over Convolution Kernels (CVPR-2020)

553 stars 91 forks source link

RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) #12

Open khawar-islam opened 3 years ago

khawar-islam commented 3 years ago

My image size is 112,112 and I got the below error. Any solution?

Line number ConvLayers/dynamic_conv.py", line 176, in forward

_x = x.view(1, -1, height, width)# 变化成一个维度进行组卷积
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...)_

Idea-in-Dream commented 3 years ago

Do you resolve this question？if you do，can you help me？

khawar-islam commented 3 years ago

@CUIMD No man, still waiting please also let me know when you find some solution